On Mon, 2 Mar 2009 16:48:28 -0800 Jeff Kirsher <[email protected]> wrote:
> On Sun, Mar 1, 2009 at 8:15 PM, Stephen Hemminger <[email protected]> > wrote: > > We are seeing problems with E1000 driver when running over VMware's emulated > > e1000 layer. These only started happening with 2.6.28 > > > >> If I disconnect an interface using the VMware's Disconnect, the link > >> appeared to have come up. If I then try to ping via the interface, I see > >> these messages: > >> > > >> > [ 264.820281] ------------[ cut here ]------------ > >> > [ 249.727468] e1000: eth1: e1000_watchdog: NIC Link is Up 1000 Mbps > >> Full Duplex, Flow Control: None > >> > [ 255.821378] e1000: eth1: e1000_clean_tx_irq: Detected Tx Unit Hang > >> > [ 255.821388] Tx Queue <0> > >> > [ 255.821390] TDH <0> > >> > [ 255.821392] TDT <1> > >> > [ 255.821393] next_to_use <1> > >> > [ 255.821395] next_to_clean <0> > >> > [ 255.821401] buffer_info[next_to_clean] > >> > [ 255.821403] time_stamp <ffffd3e0> > >> > [ 255.821405] next_to_watch <0> > >> > [ 255.821406] jiffies <ffffd4db> > >> > [ 255.821408] next_to_watch.status <0> > >> > [ 257.822189] e1000: eth1: e1000_clean_tx_irq: Detected Tx Unit Hang > >> > [ 257.822195] Tx Queue <0> > >> > [ 257.822196] TDH <0> > >> > [ 257.822198] TDT <1> > >> > [ 257.822200] next_to_use <1> > >> > [ 257.822201] next_to_clean <0> > >> > [ 257.822203] buffer_info[next_to_clean] > >> > [ 257.822204] time_stamp <ffffd3e0> > >> > [ 257.822206] next_to_watch <0> > >> > [ 257.822207] jiffies <ffffd6cf> > >> > [ 257.822209] next_to_watch.status <0> > >> > [ 259.821038] e1000: eth1: e1000_clean_tx_irq: Detected Tx Unit Hang > >> > [ 259.821043] Tx Queue <0> > >> > [ 259.821045] TDH <0> > >> > [ 259.821046] TDT <1> > >> > [ 259.821048] next_to_use <1> > >> > [ 259.821049] next_to_clean <0> > >> > [ 259.821051] buffer_info[next_to_clean] > >> > [ 259.821052] time_stamp <ffffd3e0> > >> > [ 259.821054] next_to_watch <0> > >> > [ 259.821055] jiffies <ffffd8c3> > >> > [ 259.821057] next_to_watch.status <0> > >> > [ 261.821904] e1000: eth1: e1000_clean_tx_irq: Detected Tx Unit Hang > >> > [ 261.821908] Tx Queue <0> > >> > [ 261.821910] TDH <0> > >> > [ 261.821912] TDT <1> > >> > [ 261.821913] next_to_use <1> > >> > [ 261.821915] next_to_clean <0> > >> > [ 261.821916] buffer_info[next_to_clean] > >> > [ 261.821918] time_stamp <ffffd3e0> > >> > [ 261.821920] next_to_watch <0> > >> > [ 261.821921] jiffies <ffffdab7> > >> > [ 261.821923] next_to_watch.status <0> > >> > [ 263.820721] e1000: eth1: e1000_clean_tx_irq: Detected Tx Unit Hang > >> > [ 263.820726] Tx Queue <0> > >> > [ 263.820728] TDH <0> > >> > [ 263.820730] TDT <1> > >> > [ 263.820731] next_to_use <1> > >> > [ 263.820733] next_to_clean <0> > >> > [ 263.820734] buffer_info[next_to_clean] > >> > [ 263.820736] time_stamp <ffffd3e0> > >> > [ 263.820738] next_to_watch <0> > >> > [ 263.820739] jiffies <ffffdcab> > >> > [ 263.820741] next_to_watch.status <0> > >> > [ 264.820281] ------------[ cut here ]------------ > > > > > > Stephen, > > What version of VMWare are you using? Also can you provide the > hardware info and type of interrupts you are using. We will try and > repro the issue here with the information you provide. > From Stig: On linux I've seen it with VMware Server 1.0.3. On Windows I've seen it with VMware server 1.0.5. ------------------------------------------------------------------------------ Open Source Business Conference (OSBC), March 24-25, 2009, San Francisco, CA -OSBC tackles the biggest issue in open source: Open Sourcing the Enterprise -Strategies to boost innovation and cut costs with open source participation -Receive a $600 discount off the registration fee with the source code: SFAD http://p.sf.net/sfu/XcvMzF8H _______________________________________________ E1000-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/e1000-devel
